Update app/Hackathon_setup/exp_recognition_model.py

app/Hackathon_setup/exp_recognition_model.py

@@ -18,8 +18,7 @@ logger = logging.get_logger("transformers")
 classes = {0: 'ANGER', 1: 'DISGUST', 2: 'FEAR', 3: 'HAPPINESS', 4: 'NEUTRAL', 5: 'SADNESS', 6: 'SURPRISE'}
 
 # Example Network
-class facExpRec(torch.nn.Module):
-    def __init__(self, out_features=7):
+def __init__(self, out_features=7):
         super().__init__()
 
         self.conv1 = self.convlayer(in_channels=1, out_channels=64, kernel_size=3)
@@ -28,19 +27,14 @@ class facExpRec(torch.nn.Module):
         self.conv4 = self.convlayer(in_channels=512, out_channels=512, kernel_size=3, max_pool=1)
 
         self.fc1 = self.fclayer(512, 256)
-        self.fc2 = self.fclayer(256, 512)
-        self.last = nn.Sequential(
-            nn.Linear(512, 256), 
-            nn.ReLU(),
-            nn.Linear(256, 7)
-        )
+        self.fc2 = nn.Linear(256, 7)
     
     def convlayer(self, in_channels, out_channels, kernel_size, max_pool=2):
         return nn.Sequential(
             nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=1),
             nn.BatchNorm2d(out_channels),
             nn.ReLU(),
-            nn.Dropout2d(),
+            # nn.Dropout2d(),
             nn.MaxPool2d(kernel_size=max_pool),
         )
 
@@ -48,7 +42,7 @@ class facExpRec(torch.nn.Module):
         return nn.Sequential(
             nn.Linear(in_features, out_features),
             nn.BatchNorm1d(out_features),
-            nn.Dropout1d(0.4),
+            # nn.Dropout1d(0.4),
             nn.ReLU(),
         )
 
@@ -61,7 +55,6 @@ class facExpRec(torch.nn.Module):
         x = x.view(-1, 512)
         x = self.fc1(x)
         x = self.fc2(x)
-        x = self.last(x)
         return x
         
 # Sample Helper function